Background/Aims: Inaccurate prediction of lymph node metastasis (LNM) may lead to unnecessary surgery following endoscopic resection of T1 colorectal cancer (CRC). We aimed to validate the usefulness of artificial intelligence (AI) models for predicting LNM in patients with T1 CRC. Methods: We analyzed the clinical data, laboratory results, pathological reports, and endoscopic findings of patients who underwent radical surgery for T1 CRC. We developed AI models to predict LNM using four algorithms: regularized logistic regression classifier (RLRC), random forest classifier (RFC), CatBoost classifier (CBC), and the voting classifier (VC). Four histological factors and four endoscopic findings were included to develop AI models. Areas under the receiver operating characteristics curves (AUROCs) were measured to distinguish AI model performance in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines. Results: Among 1,386 patients with T1 CRC, 173 patients (12.5%) had LNM. The AUROC values of the RLRC, RFC, CBC, and VC models for LNM prediction were significantly higher (0.673, 0.640, 0.679, and 0.677, respectively) than the 0.525 suggested in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines (vs RLRC, p<0.001; vs RFC, p=0.001; vs CBC, p<0.001; vs VC, p<0.001). The AUROC value was similar between T1 colon versus T1 rectal cancers (0.718 vs 0.615, p=0.700). The AUROC value was also similar between the initial endoscopic resection and initial surgery groups (0.581 vs 0.746, p=0.845). Conclusions AI models trained on the basis of endoscopic findings and pathological features performed well in predicting LNM in patients with T1 CRC regardless of tumor location and initial treatment method.

Background/Aims: Inaccurate prediction of lymph node metastasis (LNM) may lead to unnecessary surgery following endoscopic resection of T1 colorectal cancer (CRC). We aimed to validate the usefulness of artificial intelligence (AI) models for predicting LNM in patients with T1 CRC. Methods: We analyzed the clinical data, laboratory results, pathological reports, and endoscopic findings of patients who underwent radical surgery for T1 CRC. We developed AI models to predict LNM using four algorithms: regularized logistic regression classifier (RLRC), random forest classifier (RFC), CatBoost classifier (CBC), and the voting classifier (VC). Four histological factors and four endoscopic findings were included to develop AI models. Areas under the receiver operating characteristics curves (AUROCs) were measured to distinguish AI model performance in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines. Results: Among 1,386 patients with T1 CRC, 173 patients (12.5%) had LNM. The AUROC values of the RLRC, RFC, CBC, and VC models for LNM prediction were significantly higher (0.673, 0.640, 0.679, and 0.677, respectively) than the 0.525 suggested in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines (vs RLRC, p<0.001; vs RFC, p=0.001; vs CBC, p<0.001; vs VC, p<0.001). The AUROC value was similar between T1 colon versus T1 rectal cancers (0.718 vs 0.615, p=0.700). The AUROC value was also similar between the initial endoscopic resection and initial surgery groups (0.581 vs 0.746, p=0.845). Conclusions AI models trained on the basis of endoscopic findings and pathological features performed well in predicting LNM in patients with T1 CRC regardless of tumor location and initial treatment method.

Background/Aims: Inaccurate prediction of lymph node metastasis (LNM) may lead to unnecessary surgery following endoscopic resection of T1 colorectal cancer (CRC). We aimed to validate the usefulness of artificial intelligence (AI) models for predicting LNM in patients with T1 CRC. Methods: We analyzed the clinical data, laboratory results, pathological reports, and endoscopic findings of patients who underwent radical surgery for T1 CRC. We developed AI models to predict LNM using four algorithms: regularized logistic regression classifier (RLRC), random forest classifier (RFC), CatBoost classifier (CBC), and the voting classifier (VC). Four histological factors and four endoscopic findings were included to develop AI models. Areas under the receiver operating characteristics curves (AUROCs) were measured to distinguish AI model performance in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines. Results: Among 1,386 patients with T1 CRC, 173 patients (12.5%) had LNM. The AUROC values of the RLRC, RFC, CBC, and VC models for LNM prediction were significantly higher (0.673, 0.640, 0.679, and 0.677, respectively) than the 0.525 suggested in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines (vs RLRC, p<0.001; vs RFC, p=0.001; vs CBC, p<0.001; vs VC, p<0.001). The AUROC value was similar between T1 colon versus T1 rectal cancers (0.718 vs 0.615, p=0.700). The AUROC value was also similar between the initial endoscopic resection and initial surgery groups (0.581 vs 0.746, p=0.845). Conclusions AI models trained on the basis of endoscopic findings and pathological features performed well in predicting LNM in patients with T1 CRC regardless of tumor location and initial treatment method.

Background/Aims: Inaccurate prediction of lymph node metastasis (LNM) may lead to unnecessary surgery following endoscopic resection of T1 colorectal cancer (CRC). We aimed to validate the usefulness of artificial intelligence (AI) models for predicting LNM in patients with T1 CRC. Methods: We analyzed the clinical data, laboratory results, pathological reports, and endoscopic findings of patients who underwent radical surgery for T1 CRC. We developed AI models to predict LNM using four algorithms: regularized logistic regression classifier (RLRC), random forest classifier (RFC), CatBoost classifier (CBC), and the voting classifier (VC). Four histological factors and four endoscopic findings were included to develop AI models. Areas under the receiver operating characteristics curves (AUROCs) were measured to distinguish AI model performance in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines. Results: Among 1,386 patients with T1 CRC, 173 patients (12.5%) had LNM. The AUROC values of the RLRC, RFC, CBC, and VC models for LNM prediction were significantly higher (0.673, 0.640, 0.679, and 0.677, respectively) than the 0.525 suggested in accordance with the Japanese Society for Cancer of the Colon and Rectum guidelines (vs RLRC, p<0.001; vs RFC, p=0.001; vs CBC, p<0.001; vs VC, p<0.001). The AUROC value was similar between T1 colon versus T1 rectal cancers (0.718 vs 0.615, p=0.700). The AUROC value was also similar between the initial endoscopic resection and initial surgery groups (0.581 vs 0.746, p=0.845). Conclusions AI models trained on the basis of endoscopic findings and pathological features performed well in predicting LNM in patients with T1 CRC regardless of tumor location and initial treatment method.

Objectives: The purpose of this study was to evaluate the outcomes of implants placed in horizontally augmented alveolar ridges using porcine bone grafts and to investigate the long-term stability of the porcine bone grafts. Materials and Methods: A retrospective analysis was conducted on 49 sites that underwent horizontal ridge augmentation using porcine bone grafts and implant placement with a follow-up period longer than 5 years. Furthermore, additional analysis was conducted on 24 sites where porcine bone grafts were used exclusively for horizontal ridge augmentation and implant placement. Results: The mean follow-up period after prosthesis loading was 67.5 months, with a mean marginal bone loss of 0.23 mm at 1 year and a cumulative mean marginal bone loss of 0.40 mm over the entire follow-up period. Of the 49 implants, 2 were lost and 3 did not meet the success criteria, resulting in a survival rate of 95.9% and a success rate of 89.8%. In 24 sites, the mean marginal bone loss was 0.23 mm at 1 year and 0.41 mm at 65.8 months, with 100% survival and success rates. Conclusion Porcine bone grafts can be successfully used in horizontal ridge augmentation for implant placement in cases of ridges with insufficient horizontal width.

Purpose: Studies have yielded contradictory results on whether donor sex and donor-recipient sex disparity affect hepatocellular carcinoma (HCC) recurrence after living donor liver transplantation (LDLT). The present study assessed whether donor sex or donor-recipient sex disparity affects HCC recurrence after LDLT at a high-volume center. Methods: This study included 772 HCC patients who underwent LDLT between January 2006 and December 2015 at Asan Medical Center. Patients were divided into 4 groups based on the sex of the donor and recipient: male-to-male (n = 490, 63.5%), male-to-female (n = 75, 9.7%), female-to-male (n = 170, 22.0%), and female-to-female (n = 37, 4.8%). Results: Disease-free survival (DFS; P = 0.372) and overall survival (OS; P = 0.591) did not differ significantly among the 4 groups. DFS also did not differ significantly between LDLT recipients with male and female donors (P = 0.792) or between male and female recipients (P = 0.084). After patient matching with an α-FP/des-γ-carboxy prothrombin/tumor volume score cutoff of 5logs, donor-recipient sex disparity did not significantly affect DFS (P = 0.598) or OS (P = 0.777). There were also no differences in DFS in matched LDLT recipients with male and female donors (P = 0.312) or between male and female recipients (P = 0.374). Conclusion Neither donor sex nor donor-recipient sex disparity significantly affected posttransplant HCC recurrence.

Background: There has been no comparison of the determinants of admission route between acute ischemic stroke (AIS) and acute myocardial infarction (AMI). We examined whether factors associated with direct versus transferred-in admission to regional cardiocerebrovascular centers (RCVCs) differed between AIS and AMI. Methods: Using a nationwide RCVC registry, we identified consecutive patients presenting with AMI and AIS between July 2016 and December 2018. We explored factors associated with direct admission to RCVCs in patients with AIS and AMI and examined whether those associations differed between AIS and AMI, including interaction terms between each factor and disease type in multivariable models. To explore the influence of emergency medical service (EMS) paramedics on hospital selection, stratified analyses according to use of EMS were also performed. Results: Among the 17,897 and 8,927 AIS and AMI patients, 66.6% and 48.2% were directly admitted to RCVCs, respectively. Multivariable analysis showed that previous coronary heart disease, prehospital awareness, higher education level, and EMS use increased the odds of direct admission to RCVCs, but the odds ratio (OR) was different between AIS and AMI (for the first 3 factors, AMI > AIS; for EMS use, AMI < AIS). EMS use was the single most important factor for both AIS and AMI (OR, 4.72 vs. 3.90). Hypertension and hyperlipidemia increased, while living alone decreased the odds of direct admission only in AMI;additionally, age (65–74 years), previous stroke, and presentation during non-working hours increased the odds only in AIS. EMS use weakened the associations between direct admission and most factors in both AIS and AMI. Conclusions Various patient factors were differentially associated with direct admission to RCVCs between AIS and AMI. Public education for symptom awareness and use of EMS is essential in optimizing the transportation and hospitalization of patients with AMI and AIS.

Background/Aims: Biofeedback therapy is widely used to treat patients with chronic constipation, especially those with dyssynergic defecation. Yet, the utility of high-resolution manometry with novel parameters in the prediction of biofeedback response has not been reported. Thus, we constructed a model for predicting biofeedback therapy responders by applying the concept of integrated pressurized volume in patients undergoing high-resolution anorectal manometry. Methods: Seventy-one female patients (age: 48-68 years) with dyssynergic defecation who underwent initial high-resolution anorectal manometry and subsequent biofeedback therapy were enrolled. The manometry profiles were used to calculate the 3-dimensional integrated pressurized volumes by multiplying the distance, time, and amplitude during simulated evacuation. Partial least squares regression was performed to generate a predictive model for responders to biofeedback therapy by using the integrated pressurized volume parameters. Results: Fifty-five (77.5%) patients responded to biofeedback therapy. The responders and non-responders did not show significant differences in the conventional manometric parameters. The partial least squares regression model used a linear combination of eight integrated pressurized volume parameters and generated an area under the curve of 0.84 (95% confidence interval: 0.76-0.95, P < 0.01), with 85.5% sensitivity and 62.1% specificity. Conclusions Integrated pressurized volume parameters were better than conventional parameters in predicting the responsiveness to biofeedback therapy, and the combination of these parameters and partial least squares regression was particularly promising. Integrated pressurized volume parameters can more effectively explain the physiology of the anorectal canal compared with conventional parameters.

Objective: This study aimed to investigate whether a deep learning reconstruction (DLR) method improves the image quality, stent evaluation, and visibility of the valve apparatus in coronary computed tomography angiography (CCTA) when compared with filtered back projection (FBP) and hybrid iterative reconstruction (IR) methods. Materials and Methods: CCTA images of 51 patients (mean age ± standard deviation [SD], 63.9 ± 9.8 years, 36 male) who underwent examination at a single institution were reconstructed using DLR, FBP, and hybrid IR methods and reviewed.CT attenuation, image noise, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and stent evaluation, including 10%– 90% edge rise slope (ERS) and 10%–90% edge rise distance (ERD), were measured. Quantitative data are summarized as the mean ± SD. The subjective visual scores (1 for worst -5 for best) of the images were obtained for the following: overall image quality, image noise, and appearance of stent, vessel, and aortic and tricuspid valve apparatus (annulus, leaflets, papillary muscles, and chordae tendineae). These parameters were compared between the DLR, FBP, and hybrid IR methods. Results: DLR provided higher Hounsfield unit (HU) values in the aorta and similar attenuation in the fat and muscle compared with FBP and hybrid IR. The image noise in HU was significantly lower in DLR (12.6 ± 2.2) than in hybrid IR (24.2 ± 3.0) and FBP (54.2 ± 9.5) (p < 0.001). The SNR and CNR were significantly higher in the DLR group than in the FBP and hybrid IR groups (p < 0.001). In the coronary stent, the mean value of ERS was significantly higher in DLR (1260.4 ± 242.5 HU/mm) than that of FBP (801.9 ± 170.7 HU/mm) and hybrid IR (641.9 ± 112.0 HU/mm). The mean value of ERD was measured as 0.8 ± 0.1 mm for DLR while it was 1.1 ± 0.2 mm for FBP and 1.1 ± 0.2 mm for hybrid IR. The subjective visual scores were higher in the DLR than in the images reconstructed with FBP and hybrid IR. Conclusion DLR reconstruction provided better images than FBP and hybrid IR reconstruction.

Background/Aims: Pulmonary toxicities of coronavirus disease 2019 (COVID-19) vaccination are exceedingly rare. However, there are a few reported cases after mRNA vaccination, especially from Asian countries. The purpose of this study was to report the clinical characteristics of patients with COVID-19 vaccine-related pneumonitis (CV-P) and to review cases reported in the literature. Methods: We performed a prospective, observational case series analysis. Results: Eleven patients with a median age of 80 years were enrolled. Ten patients developed CV-P after BNT162b2-mRNA vaccination and one after ChAdOx1 nCoV-19 vaccination. We identified various patterns of CV-P, including transient infiltration, life-threatening acute respiratory distress syndrome, and aggravation of underlying interstitial lung disease. Most patients showed favorable outcomes with good responses to corticosteroid therapy. Conclusions Identifying the mechanism of CV-P requires further investigation; however, radiological and laboratory findings in our case series support inflammatory dysregulation in the lung parenchyma after vaccination. Clinicians should consider CV-P in patients with atypical lung infiltration, no specific etiologies, and recent COVID-19 vaccination